Xref: utzoo comp.ai:4591 comp.ai.neural-nets:832
Path: utzoo!utgpu!watmath!att!ucbvax!mtxinu!sybase!binky!davidvc
From: davidvc@binky.sybase.com (David Van Couvering)
Newsgroups: comp.ai,comp.ai.neural-nets
Subject: Re: Connectionism, a paradigm shift?
Message-ID: <5434@sybase.sybase.com>
Date: 8 Aug 89 18:40:27 GMT
References: <24241@iuvax.cs.indiana.edu> <568@berlioz.nsc.com> <569@berlioz.nsc.com> <705@aurora.AthabascaU.CA>
Sender: news@sybase.sybase.com
Reply-To: davidvc@binky.UUCP (David Van Couvering)
Organization: Sybase, Inc.
Lines: 24

In article <705@aurora.AthabascaU.CA> you write:
>Personally I have not decided which paradigm is better for what when yet,
>but lets remember that there may only be a superficial resemblance 
>between the operations of the brain and current neural net technology!
>A lot more things are happening in the brain (especially chemically 
>and at the intraneuron level) than are in neural nets. 
>It may even be a coincidence that what some of the functionality 
>of neural nets approximates some of the very basic perceptual-cognitive 
>functions of the brain. Some of the other functionality of neural nets 
>(extracting eigenvalues?) would not seem to match the way 
>humans do same things at all.

Hear hear!  There is still so much to know/learn about the brain
and human cognition.  For instance, the actual mechanism for
learning/memory.  For instance, the actual mechanism for pattern
recognition.  For God's sake, we don't even know what 80% of
the brain does!  Not to put down the great progress of neural
network technology, but to remember what a great realm of work
there is still to do.

David

davidvc@sybase.com
{pacbell, lll-tis, pyramid, sun}!sybase!davidvc